Open-source local AI video analyzer powered by Ollama. Visual search, automatic highlights, scene/action/object detection, audio analysis, and subtitle generation. Free, offline alternative to Twelve Labs, Runway, and Descript.

Implementation of "Look, Listen and Recognise:character-aware audio-visual subtitling"

AI 视频制作与自媒体运营工具精选合集 — 涵盖一键生成、文生视频、多平台分发、字幕翻译等 150+ 开源项目，每周更新。

Using GoogleTranslate to generate automatic subtitles of videos.

NarraPhon: Advanced Text-to-Speech Conversion Pipeline NarraPhon is a text-to-speech conversion tool. This project streamlines the process of creating audio and video (for pptx) content from multiple input formats, including PPTX (must include notes) presentations, ZIP archives containing text files, individual TXT files, and plain text.

Auto video dubbing and subtitle generation with AI-powered voice synthesis, multi-language support, and speaker-aware processing using Whisper and PyTorch.

EncodeForge — Cross-platform media processing toolkit with hardware-accelerated video encoding, AI subtitle generation, and smart file renaming.

Offline speech-to-text & speaker diarization for AI agents — Whisper ASR + MCP server + CLI + Python bindings, fully on-device, no cloud | 离线语音识别与说话人分离,Agent 开箱即用

End-to-end pipeline to translate videos with speaker diarization, subtitle generation, and voice cloning for natural voice dubbing — enhanced by LLMs for improved contextual awareness and translation quality.

a python based app that generates subtitles , and can also be translated , making use of system gpu for faster processes

🎥 Streamline video tasks with EncodeForge, a free FFmpeg GUI for batch encoding, AI subtitles, and smart media file management on all major platforms.

🎥 Translate and generate subtitles for any video in real-time, enhancing your viewing experience across multiple platforms with privacy-focused processing.

Automate subtitle generation for videos using OpenAI's Whisper API and Golang. This project extracts audio from videos, transcribes it, and embeds generated subtitles back into the videos.

Project for KEN4130 research project 1

Android APP for closed captioning with inbuilt ASR (VOSK Speech Recognition), and audio extraction using Android's native media API.

Automatic Subtitle Generation for Bengali Multimedia Using Deep Learning.

A curated list of 150+ AI-powered video creation, social media automation, and content creator tools — with comparison tables and weekly updates.

Makefile to install whisper cli on windows

🎬 CLI tool to auto-transcribe, romanize & merge subtitles from MKV files, powered by Whisper

Offline video translation and subtitle generation tools. Transcribe, translate, and generate subtitles from video content with support for multiple languages and custom glossaries.